From f472745adbe161ea4de7e3c10a5a255f4d3584ce Mon Sep 17 00:00:00 2001
From: Alan Orth <alan.orth@gmail.com>
Date: Wed, 10 Apr 2019 09:48:40 +0300
Subject: [PATCH] Update notes for 2019-04-10

---
 content/posts/2019-04.md | 15 +++++++++++++++
 docs/2019-04/index.html  | 27 ++++++++++++++++++++++++---
 docs/sitemap.xml         | 10 +++++-----
 3 files changed, 44 insertions(+), 8 deletions(-)

diff --git a/content/posts/2019-04.md b/content/posts/2019-04.md
index 5a9b00408..419bf46f7 100644
--- a/content/posts/2019-04.md
+++ b/content/posts/2019-04.md
@@ -553,5 +553,20 @@ $ psql -c 'select * from pg_stat_activity' | grep -o -E '(dspaceWeb|dspaceApi|ds
 ```
 
 - Ironically I do still see some 2 to 10% of CPU steal in `iostat 1 10`
+- Leroy from CIAT contacted me to say he knows the team who is making all those requests to CGSpace
+  - I told them how to use the REST API to get the CIAT Datasets collection and enumerate its items
+- In other news, Linode staff identified a noisy neighbor sharing our host and migrated it elsewhere last night
+
+## 2019-04-10
+
+- Abenet pointed out a possibility of validating funders against the [CrossRef API](https://support.crossref.org/hc/en-us/articles/215788143-Funder-data-via-the-API)
+- Note that if you use HTTPS and specify a contact address in the API request you have less likelihood of being blocked
+
+```
+$ http 'https://api.crossref.org/funders?query=mercator&mailto=me@cgiar.org'
+```
+
+- Otherwise, they provide the funder data in [CSV and RDF format](https://www.crossref.org/services/funder-registry/)
+- I did a quick test with the recent IITA records against reconcile-csv in OpenRefine and it matched a few, but the ones that didn't match will need a human to go and do some manual checking and informed decision making...
 
 <!-- vim: set sw=2 ts=2: -->
diff --git a/docs/2019-04/index.html b/docs/2019-04/index.html
index 25d8fba8b..5ab2866b8 100644
--- a/docs/2019-04/index.html
+++ b/docs/2019-04/index.html
@@ -38,7 +38,7 @@ $ ./delete-metadata-values.py -i /tmp/2019-02-21-delete-1-region.csv -db dspace
 <meta property="og:type" content="article" />
 <meta property="og:url" content="https://alanorth.github.io/cgspace-notes/2019-04/" />
 <meta property="article:published_time" content="2019-04-01T09:00:43&#43;03:00"/>
-<meta property="article:modified_time" content="2019-04-08T20:22:40&#43;03:00"/>
+<meta property="article:modified_time" content="2019-04-09T09:33:52&#43;03:00"/>
 
 <meta name="twitter:card" content="summary"/>
 <meta name="twitter:title" content="April, 2019"/>
@@ -81,9 +81,9 @@ $ ./delete-metadata-values.py -i /tmp/2019-02-21-delete-1-region.csv -db dspace
   "@type": "BlogPosting",
   "headline": "April, 2019",
   "url": "https://alanorth.github.io/cgspace-notes/2019-04/",
-  "wordCount": "3073",
+  "wordCount": "3218",
   "datePublished": "2019-04-01T09:00:43&#43;03:00",
-  "dateModified": "2019-04-08T20:22:40&#43;03:00",
+  "dateModified": "2019-04-09T09:33:52&#43;03:00",
   "author": {
     "@type": "Person",
     "name": "Alan Orth"
@@ -800,6 +800,27 @@ org.apache.tomcat.jdbc.pool.PoolExhaustedException: [http-bio-127.0.0.1-8443-exe
 
 <ul>
 <li>Ironically I do still see some 2 to 10% of CPU steal in <code>iostat 1 10</code></li>
+<li>Leroy from CIAT contacted me to say he knows the team who is making all those requests to CGSpace
+
+<ul>
+<li>I told them how to use the REST API to get the CIAT Datasets collection and enumerate its items</li>
+</ul></li>
+<li>In other news, Linode staff identified a noisy neighbor sharing our host and migrated it elsewhere last night</li>
+</ul>
+
+<h2 id="2019-04-10">2019-04-10</h2>
+
+<ul>
+<li>Abenet pointed out a possibility of validating funders against the <a href="https://support.crossref.org/hc/en-us/articles/215788143-Funder-data-via-the-API">CrossRef API</a></li>
+<li>Note that if you use HTTPS and specify a contact address in the API request you have less likelihood of being blocked</li>
+</ul>
+
+<pre><code>$ http 'https://api.crossref.org/funders?query=mercator&amp;mailto=me@cgiar.org'
+</code></pre>
+
+<ul>
+<li>Otherwise, they provide the funder data in <a href="https://www.crossref.org/services/funder-registry/">CSV and RDF format</a></li>
+<li>I did a quick test with the recent IITA records against reconcile-csv in OpenRefine and it matched a few, but the ones that didn&rsquo;t match will need a human to go and do some manual checking and informed decision making&hellip;</li>
 </ul>
 
 <!-- vim: set sw=2 ts=2: -->
diff --git a/docs/sitemap.xml b/docs/sitemap.xml
index f95d8b2f2..988928486 100644
--- a/docs/sitemap.xml
+++ b/docs/sitemap.xml
@@ -4,7 +4,7 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/2019-04/</loc>
-    <lastmod>2019-04-08T20:22:40+03:00</lastmod>
+    <lastmod>2019-04-09T09:33:52+03:00</lastmod>
   </url>
   
   <url>
@@ -219,7 +219,7 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/</loc>
-    <lastmod>2019-04-08T20:22:40+03:00</lastmod>
+    <lastmod>2019-04-09T09:33:52+03:00</lastmod>
     <priority>0</priority>
   </url>
   
@@ -230,7 +230,7 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/tags/notes/</loc>
-    <lastmod>2019-04-08T20:22:40+03:00</lastmod>
+    <lastmod>2019-04-09T09:33:52+03:00</lastmod>
     <priority>0</priority>
   </url>
   
@@ -242,13 +242,13 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/posts/</loc>
-    <lastmod>2019-04-08T20:22:40+03:00</lastmod>
+    <lastmod>2019-04-09T09:33:52+03:00</lastmod>
     <priority>0</priority>
   </url>
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/tags/</loc>
-    <lastmod>2019-04-08T20:22:40+03:00</lastmod>
+    <lastmod>2019-04-09T09:33:52+03:00</lastmod>
     <priority>0</priority>
   </url>